Bounded exploration — borrows its worst case framing from → H-infinity control

The paper flags bounded exploration as "related to" H-infinity control without spelling out the analogy (concrete-problems, §"Bounded Exploration:", p. 15); the connection is that both frame safety as a worst-case guarantee over a bounded set of futures rather than an average-case one. H-infinity control asks: given that disturbances to the system are bounded in magnitude, what policy minimizes the worst possible deviation from desired behavior? Bounded exploration asks a structurally similar question in RL terms: given a region of state space where even the worst action is known to be recoverable or low-harm, can the agent be allowed to act freely inside it? Both substitute a guarantee over a constrained set of possibilities for a guarantee over the single actual outcome, trading generality (the bound must be known in advance) for a hard safety floor that holds regardless of which action within the bound is taken.